{"id":"https://openalex.org/W3161656685","doi":"https://doi.org/10.1109/icassp39728.2021.9414215","title":"Speaker Embeddings for Diarization of Broadcast Data In The Allies Challenge","display_name":"Speaker Embeddings for Diarization of Broadcast Data In The Allies Challenge","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161656685","doi":"https://doi.org/10.1109/icassp39728.2021.9414215","mag":"3161656685"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002979461","display_name":"Anthony Larcher","orcid":"https://orcid.org/0000-0003-4398-0224"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Anthony Larcher","raw_affiliation_strings":["LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France"],"affiliations":[{"raw_affiliation_string":"LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065572305","display_name":"Ambuj Mehrish","orcid":"https://orcid.org/0000-0003-4240-9915"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ambuj Mehrish","raw_affiliation_strings":["LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France"],"affiliations":[{"raw_affiliation_string":"LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028709353","display_name":"Marie Tahon","orcid":"https://orcid.org/0000-0002-6782-0332"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marie Tahon","raw_affiliation_strings":["LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France"],"affiliations":[{"raw_affiliation_string":"LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075235121","display_name":"Sylvain Meignier","orcid":"https://orcid.org/0000-0001-7687-073X"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sylvain Meignier","raw_affiliation_strings":["LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France"],"affiliations":[{"raw_affiliation_string":"LIUM - EA4023, Le Mans Universit\u00e9, LE MANS CEDEX 9, France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087582941","display_name":"Jean Carrive","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125774","display_name":"Institut National de l'Audiovisuel","ror":"https://ror.org/02zwkwz55","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210125774"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean Carrive","raw_affiliation_strings":["French National Institute of Audiovisual, Paris, France"],"affiliations":[{"raw_affiliation_string":"French National Institute of Audiovisual, Paris, France","institution_ids":["https://openalex.org/I4210125774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026951519","display_name":"David Doukhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125774","display_name":"Institut National de l'Audiovisuel","ror":"https://ror.org/02zwkwz55","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210125774"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"David Doukhan","raw_affiliation_strings":["French National Institute of Audiovisual, Paris, France"],"affiliations":[{"raw_affiliation_string":"French National Institute of Audiovisual, Paris, France","institution_ids":["https://openalex.org/I4210125774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088375891","display_name":"Olivier Galibert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107682","display_name":"Laboratoire National de M\u00e9trologie et d'Essais","ror":"https://ror.org/01ph39d13","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210107682"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Galibert","raw_affiliation_strings":["Laboratoire National d\u2019Essais (LNE)","Laboratoire National d'Essais (LNE)"],"affiliations":[{"raw_affiliation_string":"Laboratoire National d\u2019Essais (LNE)","institution_ids":["https://openalex.org/I4210107682"]},{"raw_affiliation_string":"Laboratoire National d'Essais (LNE)","institution_ids":["https://openalex.org/I4210107682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":["EURECOM, Sophia Antipolis, France"],"affiliations":[{"raw_affiliation_string":"EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5002979461"],"corresponding_institution_ids":["https://openalex.org/I4210108471"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67410947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5799","last_page":"5803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7680432796478271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.765533447265625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6418858766555786},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5138259530067444},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4878518581390381},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.478512167930603},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.47824326157569885},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42880091071128845},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41691094636917114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4151776432991028},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38099533319473267},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.22242125868797302},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13235124945640564}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7680432796478271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765533447265625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6418858766555786},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5138259530067444},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4878518581390381},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.478512167930603},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.47824326157569885},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42880091071128845},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41691094636917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4151776432991028},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38099533319473267},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22242125868797302},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13235124945640564},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unive.it:10278/5105951","is_oa":false,"landing_page_url":"https://hdl.handle.net/10278/5105951","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338463","display_name":"CHIST-ERA","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W72302491","https://openalex.org/W163811496","https://openalex.org/W574052295","https://openalex.org/W1965819578","https://openalex.org/W2150769028","https://openalex.org/W2153039158","https://openalex.org/W2187012839","https://openalex.org/W2219249508","https://openalex.org/W2250641567","https://openalex.org/W2288371874","https://openalex.org/W2290266542","https://openalex.org/W2295778365","https://openalex.org/W2407024733","https://openalex.org/W2801581493","https://openalex.org/W2807305309","https://openalex.org/W2889031312","https://openalex.org/W2889233255","https://openalex.org/W2890964092","https://openalex.org/W2915347754","https://openalex.org/W2964052309","https://openalex.org/W3015783745","https://openalex.org/W3038871978","https://openalex.org/W3096084197","https://openalex.org/W6602944679","https://openalex.org/W6606699392","https://openalex.org/W6616395009","https://openalex.org/W6688816777","https://openalex.org/W6691613585","https://openalex.org/W6696958454"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2162158162","https://openalex.org/W2749720872","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2186375278"],"abstract_inverted_index":{"Diarization":[0],"consists":[1],"in":[2,50,109],"the":[3,9,54,63,86,139],"segmentation":[4],"of":[5,11,56,100,126],"speech":[6,45],"signals":[7],"and":[8,69,75,103,114,121,128],"clustering":[10],"homogeneous":[12],"speaker":[13,20,67],"segments.":[14],"State-of-the-art":[15],"systems":[16],"typically":[17,79],"operate":[18],"upon":[19],"embeddings,":[21],"such":[22],"as":[23],"i-vectors":[24,120],"or":[25,34,62],"neural":[26],"x-vectors,":[27],"extracted":[28,59],"from":[29,43,60],"mel":[30],"cepstral":[31],"coefficients":[32],"(MFCCs)":[33],"spectrograms.":[35],"The":[36,47],"recent":[37],"SincNet":[38,117,135],"architecture":[39],"extracts":[40],"x-vectors":[41,118,122,136],"directly":[42],"raw":[44,64],"signals.":[46],"work":[48],"reported":[49],"this":[51],"paper":[52],"compares":[53],"performance":[55],"different":[57],"embeddings":[58,142],"MFCCs":[61],"signal":[65],"for":[66],"diarization":[68],"broadcast":[70,101],"media":[71],"treated":[72],"with":[73,85,112],"compression":[74,113],"sub-sampling,":[76],"operations":[77],"which":[78],"degrade":[80],"performance.":[81],"Experiments":[82],"are":[83,137,144],"performed":[84],"new":[87],"ALLIES":[88],"database":[89],"that":[90,134],"was":[91],"designed":[92],"to":[93,147],"complement":[94],"existing,":[95],"publicly":[96],"available":[97],"French":[98],"corpora":[99],"radio":[102],"TV":[104],"shows.":[105],"Results":[106],"show":[107],"that,":[108],"adverse":[110],"conditions,":[111],"sampling":[115],"mismatch,":[116],"outperform":[119],"by":[123],"relative":[124],"DERs":[125],"43%":[127],"73%":[129],"respectively.":[130],"Additionally":[131],"we":[132],"found":[133],"not":[138],"absolute":[140],"best":[141],"but":[143],"more":[145],"robust":[146],"data":[148],"mismatch":[149],"than":[150],"others.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}